Enter opens the highlighted result. Esc closes.

o4 Mini vs Qwen2.5 72B Instruct

o4 Mini leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 16.7 to 7.7, and Qwen2.5 72B Instruct costs 11.0x less per output token ($0.40 vs $4.40 per million). Updated October 22, 2026; 45 benchmarks have a result for both.

Replace o4 Mini Replace Qwen2.5 72B Instruct
o4 MiniOpenAI
Coding
No data
Overall
43.0
Output $/M
$4.40
45
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
vs boards won of 45 shared

o4 Mini or Qwen2.5 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick o4 Mini for a larger context window (200K against 33K tokens).

Model Ao4 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
45
o4 Mini only
53
Qwen2.5 72B Instruct only
8
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
o4 Mini not benchmarked, Qwen2.5 72B Instruct not benchmarked.
Widest category
Math, 49.0 points apart on average over 6 shared benchmarks.
Widest single gap
AA Math Index: o4 Mini 90.7 against Qwen2.5 72B Instruct 14.0, 76.7 points apart on a 0 to 100 scale.
Output price
o4 Mini $4.40 against Qwen2.5 72B Instruct $0.40 per million output tokens, 11.0x apart.
Context window
o4 Mini takes 200K tokens, Qwen2.5 72B Instruct 33K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Categoryo4 MiniBarsQwen2.5 72B InstructTies
Coding50
Intelligence20
Agentic work20
Reasoning60
Math60
Knowledge50
General190
All shared boards450
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
Aider polyglot72.0%Not measuredOnly o4 Mini measured
SWE-bench Verified64.6%Not measuredOnly o4 Mini measured
SWE-bench Multimodal33.9%Not measuredOnly o4 Mini measured
LiveCodeBench (Vals AI)82.2%Not measuredOnly o4 Mini measured
LiveCodeBench (Artificial Analysis run)85.9%27.6%o4 Mini
Terminal-Bench Hard (Artificial Analysis run)15.2%4.5%o4 Mini
GSO-Bench3.6%Not measuredOnly o4 Mini measured
WeirdML52.6%16.0%o4 Mini
LMArena Text: coding13681292o4 Mini
LMArena Text: software and IT13671292o4 Mini
SciCode10.8%Not measuredOnly o4 Mini measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
AA Intelligence Index16.77.7o4 Mini
Epoch Capabilities Index145.5129.0o4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
τ²-Bench Telecom55.6%34.5%o4 Mini
METR time horizons63.9%35.8%o4 Mini
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Berkeley Function Calling Leaderboard (BFCL)53.2%Not measuredOnly o4 Mini measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
GPQA Diamond74.5%Not measuredOnly o4 Mini measured
MMMU Pro (Vals AI)79.7%Not measuredOnly o4 Mini measured
GPQA Diamond (Artificial Analysis run)78.4%49.1%o4 Mini
Humanity's Last Exam (Artificial Analysis run)16.5%3.6%o4 Mini
GPQA Diamond (Epoch AI run)79.6%49.1%o4 Mini
ARC-AGI58.7%Not measuredOnly o4 Mini measured
ARC-AGI-26.1%Not measuredOnly o4 Mini measured
SimpleBench38.7%Not measuredOnly o4 Mini measured
Chess puzzles22.0%Not measuredOnly o4 Mini measured
Mystery game puzzles5.0%Not measuredOnly o4 Mini measured
VPCT57.5%Not measuredOnly o4 Mini measured
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts13511271o4 Mini
LMArena Text: expert13431245o4 Mini
LMArena Text: hard prompts in English13661279o4 Mini
LMArena Vision: diagrams1197Not measuredOnly o4 Mini measured
LMArena Vision: homework1234Not measuredOnly o4 Mini measured
Kagi LLM Benchmark67.6%Not measuredOnly o4 Mini measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
AIME83.7%Not measuredOnly o4 Mini measured
MATH 500 (Vals AI)94.2%Not measuredOnly o4 Mini measured
MGSM (Vals AI)93.4%Not measuredOnly o4 Mini measured
AA Math Index90.714.0o4 Mini
AIME 2025 (Artificial Analysis run)90.7%14.0%o4 Mini
OTIS Mock AIME81.7%8.1%o4 Mini
FrontierMath, tiers 1 to 336.1%Not measuredOnly o4 Mini measured
FrontierMath, tier 44.9%Not measuredOnly o4 Mini measured
MATH level 597.8%63.2%o4 Mini
LMArena Text: math13891283o4 Mini
LMArena Text: mathematical work13791290o4 Mini
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
MMLU Pro80.6%Not measuredOnly o4 Mini measured
LegalBench (Vals AI)79.2%Not measuredOnly o4 Mini measured
CorpFin (Vals AI)59.0%Not measuredOnly o4 Mini measured
TaxEval (Vals AI)74.8%Not measuredOnly o4 Mini measured
MortgageTax (Vals AI)64.8%Not measuredOnly o4 Mini measured
MedQA (Vals AI)96.0%Not measuredOnly o4 Mini measured
MedCode (Vals AI)33.8%Not measuredOnly o4 Mini measured
MMLU Pro (Artificial Analysis run)83.2%72.0%o4 Mini
SimpleQA Verified19.6%Not measuredOnly o4 Mini measured
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
GeoBench64.0%Not measuredOnly o4 Mini measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science13541275o4 Mini
LMArena Text: medicine and healthcare13611258o4 Mini
LMArena Text: legal and government13501288o4 Mini
LMArena Text: business and finance13251253o4 Mini
FACTS Benchmark Suite28.1%Not measuredOnly o4 Mini measured
Neither model has a result on the other 1 board here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
Design Arena: websites985Not measuredOnly o4 Mini measured
Design Arena: UI components983Not measuredOnly o4 Mini measured
Design Arena: game dev1003Not measuredOnly o4 Mini measured
Design Arena: data viz991Not measuredOnly o4 Mini measured
Design Arena: 3D854Not measuredOnly o4 Mini measured
Design Arena: all code categories976Not measuredOnly o4 Mini measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
SAGE (Vals AI)41.1%Not measuredOnly o4 Mini measured
MedScribe (Vals AI)69.1%Not measuredOnly o4 Mini measured
IFBench68.7%36.9%o4 Mini
Long context reasoning (AA-LCR)61.0%Not measuredOnly o4 Mini measured
DTBench77.6%62.9%o4 Mini
LMCA26.5%13.4%o4 Mini
Fiction.LiveBench77.8%Not measuredOnly o4 Mini measured
Creative writing (Lech Mazur)75.0%Not measuredOnly o4 Mini measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text13531269o4 Mini
LMArena Text: instruction following13201254o4 Mini
LMArena Text: creative writing12941221o4 Mini
LMArena Vision1194Not measuredOnly o4 Mini measured
LMArena Text: English13671283o4 Mini
LMArena Text: non-English13371252o4 Mini
LMArena Text: Chinese13541273o4 Mini
LMArena Text: German13361234o4 Mini
LMArena Text: Japanese13081180o4 Mini
LMArena Text: Korean13121188o4 Mini
LMArena Text: French13641280o4 Mini
LMArena Text: Spanish13461255o4 Mini
LMArena Text: Russian13341264o4 Mini
LMArena Text: Polish1358Not measuredOnly o4 Mini measured
LMArena Text: multi-turn13501272o4 Mini
LMArena Text: longer queries13151281o4 Mini
LMArena Text: writing and language13161247o4 Mini
LMArena Text: entertainment and media13081211o4 Mini
LMArena Vision: English1200Not measuredOnly o4 Mini measured
LMArena Vision: Chinese1218Not measuredOnly o4 Mini measured
LMArena Vision: reading text1197Not measuredOnly o4 Mini measured
LMArena Vision: humor1199Not measuredOnly o4 Mini measured
LMArena Vision: captioning1204Not measuredOnly o4 Mini measured
LMArena Vision: recognizing things1218Not measuredOnly o4 Mini measured
LMArena Vision: creative writing1166Not measuredOnly o4 Mini measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for o4 Mini and Qwen2.5 72B Instruct
Benchmarko4 MiniQwen2.5 72B InstructLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

o4 Mini$0.0033Fits in one request
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

o4 Mini$0.068Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

Qwen2.5 72B Instruct costs less

Agent loop

200K input + 10K output tokens

o4 Mini$0.264Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

Qwen2.5 72B Instruct costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of o4 Mini and Qwen2.5 72B Instruct
SpecificationOpenAI o4 MiniQwen2.5 72B Instruct
MakerOpenAIQwen
WeightsNo public weights listedOpen weights
ReleasedApril 16, 2025September 19, 2024
Context window200K33K
Input $/Mtok$1.10$0.36
Output $/Mtok$4.40$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is o4 Mini better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick o4 Mini for a larger context window (200K against 33K tokens).

Which is cheaper, o4 Mini or Qwen2.5 72B Instruct?

o4 Mini costs $1.10 per million input tokens and $4.40 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, o4 Mini or Qwen2.5 72B Instruct?

o4 Mini, with 200K tokens against 33K.

How many benchmarks is the o4 Mini vs Qwen2.5 72B Instruct comparison based on?

45 benchmarks have a result for both models as of October 22, 2026. o4 Mini's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next